commit 2b52b4ad78fd2977dbd9dea1a07a836e8a88182e Author: ModelHub XC Date: Sun Apr 12 18:16:55 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/IBM-GPT-5.4-Coder-1B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d9c4827 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +IBM-GPT-5.4-Coder-1B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +IBM-GPT-5.4-Coder-1B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +IBM-GPT-5.4-Coder-1B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +IBM-GPT-5.4-Coder-1B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +IBM-GPT-5.4-Coder-1B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +IBM-GPT-5.4-Coder-1B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +IBM-GPT-5.4-Coder-1B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +IBM-GPT-5.4-Coder-1B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +IBM-GPT-5.4-Coder-1B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +IBM-GPT-5.4-Coder-1B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +IBM-GPT-5.4-Coder-1B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +IBM-GPT-5.4-Coder-1B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/IBM-GPT-5.4-Coder-1B.IQ4_XS.gguf b/IBM-GPT-5.4-Coder-1B.IQ4_XS.gguf new file mode 100644 index 0000000..cdcc98d --- /dev/null +++ b/IBM-GPT-5.4-Coder-1B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c06c069ed5dfe7e94e220dd7c52b44ac3f2b76ce8020f8806a0075162b2ab035 +size 943529024 diff --git a/IBM-GPT-5.4-Coder-1B.Q2_K.gguf b/IBM-GPT-5.4-Coder-1B.Q2_K.gguf new file mode 100644 index 0000000..1dffaf3 --- /dev/null +++ b/IBM-GPT-5.4-Coder-1B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0c433f5e0037424c7295121d4d00363076e9083c3e9a30c55687804992d0294 +size 701701184 diff --git a/IBM-GPT-5.4-Coder-1B.Q3_K_L.gguf b/IBM-GPT-5.4-Coder-1B.Q3_K_L.gguf new file mode 100644 index 0000000..893db2d --- /dev/null +++ b/IBM-GPT-5.4-Coder-1B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6640d3e30623aff1d9225e07832468e0f7c786d6d787b57aae147e523910c38d +size 926161984 diff --git a/IBM-GPT-5.4-Coder-1B.Q3_K_M.gguf b/IBM-GPT-5.4-Coder-1B.Q3_K_M.gguf new file mode 100644 index 0000000..3025bd7 --- /dev/null +++ b/IBM-GPT-5.4-Coder-1B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74372d9ea469aa2f56b28a427f55a1b0922fd29a5b2921e633dd793a6629daaf +size 860363840 diff --git a/IBM-GPT-5.4-Coder-1B.Q3_K_S.gguf b/IBM-GPT-5.4-Coder-1B.Q3_K_S.gguf new file mode 100644 index 0000000..9e2084e --- /dev/null +++ b/IBM-GPT-5.4-Coder-1B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b158325a67f1b309ce629e4fea324b4f83cb8ff4950672df003459dc656fb827 +size 785587264 diff --git a/IBM-GPT-5.4-Coder-1B.Q4_K_M.gguf b/IBM-GPT-5.4-Coder-1B.Q4_K_M.gguf new file mode 100644 index 0000000..668707b --- /dev/null +++ b/IBM-GPT-5.4-Coder-1B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a44880d41fcd96c131fa628dd2c5d0ca7442612388e7b05993f8b89ab0912502 +size 1023646784 diff --git a/IBM-GPT-5.4-Coder-1B.Q4_K_S.gguf b/IBM-GPT-5.4-Coder-1B.Q4_K_S.gguf new file mode 100644 index 0000000..8f168b7 --- /dev/null +++ b/IBM-GPT-5.4-Coder-1B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72be1ebbf51a601b72fc4a5bf562690e9c47e608f19d43b2b9a9a302a4e07e16 +size 980753472 diff --git a/IBM-GPT-5.4-Coder-1B.Q5_K_M.gguf b/IBM-GPT-5.4-Coder-1B.Q5_K_M.gguf new file mode 100644 index 0000000..c0f1569 --- /dev/null +++ b/IBM-GPT-5.4-Coder-1B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:655cd0afd1de109bd7ce40b75f27cdc9a0a629ec38646f8a4a3eb78f16e40058 +size 1178311744 diff --git a/IBM-GPT-5.4-Coder-1B.Q5_K_S.gguf b/IBM-GPT-5.4-Coder-1B.Q5_K_S.gguf new file mode 100644 index 0000000..29f2abf --- /dev/null +++ b/IBM-GPT-5.4-Coder-1B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57c9c1edd921a7d14a25ec1364e5c4d624a6a7dda2a58cb9fa3c174f4d3a79d8 +size 1153244224 diff --git a/IBM-GPT-5.4-Coder-1B.Q6_K.gguf b/IBM-GPT-5.4-Coder-1B.Q6_K.gguf new file mode 100644 index 0000000..9b0e131 --- /dev/null +++ b/IBM-GPT-5.4-Coder-1B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1b2d483711395f1d90085e1285b9968ad37d3ee0978249aa0ee2bc887c29dfc +size 1342643264 diff --git a/IBM-GPT-5.4-Coder-1B.Q8_0.gguf b/IBM-GPT-5.4-Coder-1B.Q8_0.gguf new file mode 100644 index 0000000..4166eae --- /dev/null +++ b/IBM-GPT-5.4-Coder-1B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:020f6c8cdd04f74dd6051ccf26c009c93bcda87a6865054a47cc2b60ec6ae6b4 +size 1737792576 diff --git a/IBM-GPT-5.4-Coder-1B.f16.gguf b/IBM-GPT-5.4-Coder-1B.f16.gguf new file mode 100644 index 0000000..188092a --- /dev/null +++ b/IBM-GPT-5.4-Coder-1B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34c09751bfcf352860396a55c2c009f1794f8f4c718a092ff2a4e7b0b090c8f0 +size 3267402816 diff --git a/README.md b/README.md new file mode 100644 index 0000000..267e903 --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: gss1147/IBM-GPT-5.4-Coder-1B +datasets: +- Roman1111111/gpt-5.4-step-by-step-reasoning +- TeichAI/gpt-5.1-codex-max-1000x +- TeichAI/gpt-5.1-high-reasoning-1000x +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- granite +- ibm +- full-finetune +- dual-gpu +- code +- reasoning +- text-generation +--- +## About + + + + + + + + + +static quants of https://huggingface.co/gss1147/IBM-GPT-5.4-Coder-1B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#IBM-GPT-5.4-Coder-1B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/IBM-GPT-5.4-Coder-1B-i1-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/IBM-GPT-5.4-Coder-1B-GGUF/resolve/main/IBM-GPT-5.4-Coder-1B.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/IBM-GPT-5.4-Coder-1B-GGUF/resolve/main/IBM-GPT-5.4-Coder-1B.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/IBM-GPT-5.4-Coder-1B-GGUF/resolve/main/IBM-GPT-5.4-Coder-1B.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/IBM-GPT-5.4-Coder-1B-GGUF/resolve/main/IBM-GPT-5.4-Coder-1B.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/IBM-GPT-5.4-Coder-1B-GGUF/resolve/main/IBM-GPT-5.4-Coder-1B.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/IBM-GPT-5.4-Coder-1B-GGUF/resolve/main/IBM-GPT-5.4-Coder-1B.Q4_K_S.gguf) | Q4_K_S | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/IBM-GPT-5.4-Coder-1B-GGUF/resolve/main/IBM-GPT-5.4-Coder-1B.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/IBM-GPT-5.4-Coder-1B-GGUF/resolve/main/IBM-GPT-5.4-Coder-1B.Q5_K_S.gguf) | Q5_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/IBM-GPT-5.4-Coder-1B-GGUF/resolve/main/IBM-GPT-5.4-Coder-1B.Q5_K_M.gguf) | Q5_K_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/IBM-GPT-5.4-Coder-1B-GGUF/resolve/main/IBM-GPT-5.4-Coder-1B.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/IBM-GPT-5.4-Coder-1B-GGUF/resolve/main/IBM-GPT-5.4-Coder-1B.Q8_0.gguf) | Q8_0 | 1.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/IBM-GPT-5.4-Coder-1B-GGUF/resolve/main/IBM-GPT-5.4-Coder-1B.f16.gguf) | f16 | 3.4 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +